Determined AI · Agentic Access

Determined AI Agentic Access

x-agentic-access generated

Determined AI exposes 10 API operations that an AI agent could call, of which 2 are state-changing ‘acting’ operations. This is a recommended x-agentic-access execution contract — the scope, audience, consequence tier, short-lived token constraints, and escalation each action should carry before it is handed to an autonomous agent.

By consequence: 8 read and 2 write.

Contracts are classified heuristically from the provider’s OpenAPI and refresh on every APIs.io network build; audience is bound per deployment. The model follows Curity’s Access Intelligence (apidays Munich 2026). Browse every provider’s agent contracts at agentic-access.apis.io.

Artificial IntelligenceDeep LearningMachine LearningMLOps

Operations: 10 Acting: 2 Human-in-the-loop: 0 Method: generated

By consequence

read 8 write 2

Source

Agentic Access

generated: '2026-07-15'
method: generated
source: openapi/determined-ai-openapi.yml
description: Recommended x-agentic-access execution contracts, classified heuristically from
  the OpenAPI. A governance starting point for exposing this API to AI agents — review and bind
  audience per deployment. See research/curity/agentic-governance/.
summary:
  operations: 10
  by_action_class:
    acting: 2
    connected: 8
  by_consequence:
    write: 2
    read: 8
  human_in_the_loop_required: 0
operations:
- path: /api/v1/auth/login
  method: post
  operationId: login
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /api/v1/auth/logout
  method: post
  operationId: logout
  x-agentic-access:
    action-class: acting
    consequence: write
    subject: required
    audience: null
    token:
      max-ttl: 900
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /api/v1/users
  method: get
  operationId: getUsers
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/cluster
  method: get
  operationId: getClusterInfo
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/experiments
  method: get
  operationId: getExperiments
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/experiments/{experimentId}
  method: get
  operationId: getExperiment
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/models
  method: get
  operationId: getModels
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/checkpoints/{checkpointUuid}
  method: get
  operationId: getCheckpoint
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/templates
  method: get
  operationId: getTemplates
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/tokens
  method: get
  operationId: getAccessTokens
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none